vmarkovtsev

import os
import sys
import matplotlib
matplotlib.use('cairo')
from matplotlib import pyplot
from matplotlib.colors import LinearSegmentedColormap
import numpy
from scipy.cluster.hierarchy import linkage, leaves_list
import xmltodict

vmarkovtsev

Большая подборка иконочных веб-шрифтов (free) и их генераторов.

https://www.google.com/design/icons/
(Лицензия: CC BY 4.0)

https://linearicons.com/free
(Лицензия: Custom)

https://octicons.github.com/

vmarkovtsev

Domains

First of all. ML has two quite different activity domains:

1. Running something on many repositories.
2. Running something on a single repository

Depending on the size of (2), it makes or does not make sense to launch Spark. For example, consider the topic model application scenario:

vmarkovtsev

Recently, GitHub introduced the change in how atx headers are parsed in Markdown files.

##Wrong

Correct

While this change follows the spec, it breaks many existing repositories. I took the README dataset which we created at source{d} and ran a simple

vmarkovtsev

import re
NAME_BREAKUP_RE = re.compile(r"[^a-zA-Z]+")

def extract_names(token):
    token = token.strip()
    prev_p = [""]

    def ret(name):
        r = name.lower()
        if len(name) >= 3:

vmarkovtsev

package hercules

import (
	"gopkg.in/src-d/go-git.v4"
	"gopkg.in/src-d/go-git.v4/plumbing/object"
	"gopkg.in/src-d/hercules.v4/internal/core"
	"gopkg.in/src-d/hercules.v4/internal/plumbing"
	"gopkg.in/src-d/hercules.v4/internal/plumbing/identity"
	"gopkg.in/src-d/hercules.v4/internal/plumbing/uast"
	"gopkg.in/src-d/hercules.v4/internal/yaml"

vmarkovtsev

{
  "embeddings": [
    {
      "tensorName": "GitLab developer experience clusters",
      "tensorShape": [
        173,
        258
      ],
      "tensorPath": "https://gist.githubusercontent.com/vmarkovtsev/4bd05fdd761e49a7bbbca87381e65c9c/raw/38801e9740529ac2c9ac7884fc3e8623bb37caad/data.tsv",
      "metadataPath": "https://gist.githubusercontent.com/vmarkovtsev/4bd05fdd761e49a7bbbca87381e65c9c/raw/38801e9740529ac2c9ac7884fc3e8623bb37caad/meta.tsv"

vmarkovtsev

vmarkovtsev

from typing import Tuple, Union

import numpy as np
from skimage.draw import line_aa
import tensorflow as tf


def create_motion_blur_kernel(dim: int, angle: float) -> tf.Tensor:
    # Define a disk which contains the dim x dim square
    radius = np.sqrt(0.5 * dim**2)

vmarkovtsev

import matplotlib.pyplot as plt
plt.rcParams["image.cmap"] = "hot"

# 25x25 kernel pointing straight to the east
dim = 25
kernel = np.squeeze(create_motion_blur_kernel(dim, (90/180) * np.pi).numpy()[:, :, 0, 0])
plt.contourf(np.linspace(-dim//2, dim//2, dim), np.linspace(-dim//2, dim//2, dim), kernel)
plt.colorbar()
plt.show()